Abstract
Pulse-shape discrimination plays a key role in improving the signal-to-background ratio in NEOS analysis by removing fast neutrons. Identifying particles by looking at the tail of the waveform has been an effective and plausible approach for pulse-shape discrimination, but has the limitation in sorting low energy particles. As a good alternative, the convolutional neural network can scan the entire waveform as they are to recognize the characteristics of the pulse and perform shape classification of NEOS data. This network provides a powerful identification tool for all energy ranges and helps to search unprecedented phenomena of low-energy, a few MeV or less, neutrinos.
Similar content being viewed by others
References
G. Mention et al., Phys. Rev. D 83, 073006 (2011).
P. Adamson et al. [Daya Bay and MINOS], Phys. Rev. Lett. 117, 151801 (2016).
G. Bak et al. [RENO], Phys. Rev. Lett. 122, 232501 (2019).
P. Adamson et al. [MINOS+ and Daya Bay], Phys. Rev. Lett. 125, 071801 (2020).
Y. J. Ko et al. [NEOS], Phys. Rev. Lett. 118, 121802 (2017).
Y. Oh, NEOS result and prospects. Zenodo. https://doi.org/10.5281/zenodo.1286994 (June 2018).
J. Ashenfelter et al. [PROSPECT], arXiv:1806.02784 [hep-ex].
Y. Abreu et al. [SoLid], J. Instrum. 12, P04024 (2017).
I. Alekseev et al. [DANSS], Phys. Lett. B 787, 56 (2018).
H. Almazn et al. [STEREO], Phys. Rev. Lett. 121, 161801 (2018)
Y. J. Ko, Status of NEOS-II. Zenodo. https://doi.org/10.5281/zenodo.3959599 (June 2020).
Y. Ko et al. [NEOS], J. Phys. Conf. Ser. 1216, 012004 (2019).
D. A. Dwyer and T. J. Langford, Phys. Rev. Lett. 114, 012502 (2015).
D. Adey et al. [Daya Bay], Phys. Rev. Lett. 123, 111801 (2019).
J. Y. Kim et al. [NEOS], in preparation.
B. R. Kim et al. [NEOS], Phys. Scr. 90, 055302 (2015).
Y. J. Ko et al. [NEOS], J. Korean Phys. Soc. 69, 1651 (2016).
J. Griffiths et al., arXiv:1807.06853 [physics.ins-det].
P. Holl et al., Eur. Phys. J. C 79, 450 (2019).
B. Abi et al. [DUNE], arXiv:2006.15052 [physics.ins-det].
S. Alonso-Monsalve et al., arXiv:2009.00688 [hep-ex].
https://github.com/tensorflow/tensorflow/releases/tag/v2.2.1
D. P. Kangma and J. Ba, arXiv:1412.6980v9 [cs.LG].
Acknowledgments
Y. Jeong and K. Siyeon thank C. Ha for helpful advice and discussion. This research was supported by the National Research Foundation Grant of Korea (NRF-2017R1A2B4004308), IBS-R016-D1, and the Chung-Ang University Graduate Research Scholarship in 2019.
Author information
Authors and Affiliations
Consortia
Corresponding author
Rights and permissions
About this article
Cite this article
Jeong, Y., Han, B.Y., Jeon, E.J. et al. Pulse-shape Discrimination of Fast Neutron Background using Convolutional Neural Network for NEOS II. J. Korean Phys. Soc. 77, 1118–1124 (2020). https://doi.org/10.3938/jkps.77.1118
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3938/jkps.77.1118